Chapter 11: Correlational Research
Differential Analysis
Technique of using moderator variables to form subgroups when examining the relationship between two other variables
Correlational research is primarily intended for determining
how variations in a sample's score on one measure are related to variations in their scores on one or more other variables
As a correlation coefficient increases in size, it means that
scores on one variable are better able to predict scores on the other variable
Scattergram/Scatterplot
A graph of the relationship between two variables
Multiple Regression
A mathematical technique that enables researchers to determine (1) how well the scores for each of a set of measured independent variables predict the scores on the measured dependent variable and (2) how well the combination of scores for all the measured independent variables predict the scores on the measured variables
Nesting
A situation in which a variable exists at several levels of an organizational structure
Canonical Correlation
A specialized type of multiple regression used when there are multiple dependent variables that can be viewed as different facets of an underlying factor
Tetrachoric Correlation Coefficient
A statistic used to describe the magnitude of the relationship between two variables, both of which yield scores that can be split into artificial dichotomies
Linear Correlation
A statistical approach for analyzing the distribution of a sample's scores on two measures, based on the assumption that as scores on one distribution increase, scores on the other distribution will also increase or decrease throughout the range of the score distribution
Prediction Research
A type of investigation that involves the use of data collected at one point in time to predict future behavior or events
Discriminant Analysis
A type of multiple regression that enables researchers to determine how well scores on several independent variables predict scores on a dependent variable when those scores are in the form of categories
Correlational Research
A type of quantitative investigation that seeks to discover the direction and degree of the relationship among variables, typically by the use of correlational statistics
Continuous Variable
A variable all of whose values have been measured and used by researchers; can assume different values between each point Ex: height
Discrete Variable
A variable with fixed values Ex: number of children
Negative Correlation
Any situation in which higher scores on a measure of one variable are linked to lower scores on a measure of another variable
Logistic Regression Analysis
Can be used for the same purpose as discriminate analysis but is more commonly used when the dependent variable is dichotomous
Dichotomous Variable
Can only have two values
True Dichotomy
Has only two possible variables in reality Ex: high school graduation (graduated or not graduated)
Artificial Dichotomy
Has only two values because they have been created by researchers or others
Effect Size
Helpful in determining the practical significance of statistical results
Bivariate Correlational Statistics
Indicates the magnitude of relationship between two, and only two, variables
Test of Statistical Significance
Indicates the likelihood that the statistical results obtained from the research sample are chance deviations from the results that would have been obtained if the researchers had studied the entire population that the sample represents
Multivariate Correlation
Involves a statistical analysis of the relationship between three or more variables
Line of Best Fit
Lines that allows for the best prediction of an individual's score on the y axis from knowing her score on the x axis
Correlation Coefficient
Mathematical expression that provides information about the direction and magnitude of the relationship between a sample's scores on measures of two or more variables; can range in value from -1.00 to +1.00
Criterion Variable
Measured at a subsequent point in time and is the outcome that researchers are trying to predict
Path Analysis/Structural Equation Modeling
Multivariate techniques for testing causal links among different variables that have been measured
Positive Correlation
Occurs when higher scores on a measure of one variable are associated with higher scores on a measure of the other variable
Independent Variable
Presumed cause in a causal relationship
Dependent Variable
Presumed effect
Moderator Variable
Presumed to affect the strength or direction, or both, of the correlation between two other variables
Factor Analysis
Purpose it to determine whether a set of variables reflects a smaller number of underlying factors
Correlation Matrix
Shows the correlation coefficient for all pairs of variables that were measured
Pearson Product-Moment Correlation Coefficient (r)
Statistic that indicates the direction and magnitude of a relationship between a sample's distribution of scores on two measures
Hierarchical Linear Modeling (HLM)
Statistical technique that enables researchers to determine how the correlation between two variables is affected by the different levels of nesting
Curvilinear Correlation
The line of best fit forms a curve, such that low values of variable A are associated with low values of variable B, medium values of variable A are associated with high values of variable B, and high values of variable A are associated with low values of variable B
Nonlinear Correlation
Variables are correlated with each other, but not in a linear manner
Predictor Variable
Variables that are measured in one point in time and then correlated with a criterion variable
Correlational research...
can be used to explore causal relationships
If researchers wish to determine whether the correlation between two variables is affected by different levels of "nesting," the appropriate statistical technique would be
hierarchical linear modeling
In their report of a correlational study, researchers should
identify and discuss flaws in the study
A correlational research design can include
multiple predictor variables
If researchers wish to determine the influence of multiple independent variables on a single dependent variable, the appropriate statistical technique would be
multiple regression
Inspection of a scattergram provides information about whether
the correlation between two variables is linear or nonlinear
A correlational coefficient provides information about
the magnitude and direction of the relationship between two variables but not its linearity
The null hypothesis in a typical correlational study states that
the true correlation coefficient in the population represented by the research sample is zero